© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 40311
    Prev
    Next
    INDEX
    Explanations

    wise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONGL
    -0.30
    argent
    -0.27
    ç¿®
    -0.27
    mina
    -0.26
     minority
    -0.25
    Dig
    -0.24
    lle
    -0.24
     Sox
    -0.24
    æĮĸæİĺ
    -0.24
     ÑĢеклам
    -0.23
    POSITIVE LOGITS
    urat
    0.27
    aret
    0.25
    able
    0.25
    åıijçĶŁåľ¨
    0.25
    éĿ¢å¯¹
    0.25
    ulet
    0.24
    adge
    0.24
    natural
    0.24
     being
    0.23
     gegenüber
    0.23
    Activations Density 0.094%

    No Known Activations